Ma YL, Li HG, Xu JX, Xu X, Lu D. Letter to the Editor: Early complications in split liver transplantation: An interpretable machine learning model requires multicenter validation. World J Gastroenterol 2026; 32(23): 116868 [DOI: 10.3748/wjg.v32.i23.116868]
Corresponding Author of This Article
Di Lu, Department of Hepatobiliary & Pancreatic Surgery and Minimally Invasive Surgery, Zhejiang Provincial People's Hospital, No. 158 Shangtang Road, Hangzhou 310014, Zhejiang Province, China. zjuludi@zju.edu.cn
Research Domain of This Article
Surgery
Article-Type of This Article
letter
Open-Access Policy of This Article
This article is an open-access article which was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution Non Commercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See: http://creativecommons.org/licenses/by-nc/4.0/
Baishideng Publishing Group Inc, 7041 Koll Center Parkway, Suite 160, Pleasanton, CA 94566, USA
Share the Article
Ma YL, Li HG, Xu JX, Xu X, Lu D. Letter to the Editor: Early complications in split liver transplantation: An interpretable machine learning model requires multicenter validation. World J Gastroenterol 2026; 32(23): 116868 [DOI: 10.3748/wjg.v32.i23.116868]
World J Gastroenterol. Jun 21, 2026; 32(23): 116868 Published online Jun 21, 2026. doi: 10.3748/wjg.v32.i23.116868
Letter to the Editor: Early complications in split liver transplantation: An interpretable machine learning model requires multicenter validation
Yu-Le Ma, Hui-Gang Li, Jin-Xin Xu, Xiao Xu, Di Lu
Yu-Le Ma, School of Clinical Medicine, Hangzhou Medical College, Hangzhou 310000, Zhejiang Province, China
Hui-Gang Li, Institute of Translational Medicine, Zhejiang University School of Medicine, Hangzhou 310058, Zhejiang Province, China
Jin-Xin Xu, The Second School of Clinical Medicine, Zhejiang Chinese Medical University, Hangzhou 310053, Zhejiang Province, China
Xiao Xu, NHC Key Laboratory of Combined Multi-Organ Transplantation, Institute of Organ Transplantation, Zhejiang University School of Medicine, Hangzhou 310003, Zhejiang Province, China
Di Lu, Department of Hepatobiliary & Pancreatic Surgery and Minimally Invasive Surgery, Zhejiang Provincial People's Hospital, Hangzhou 310014, Zhejiang Province, China
Author contributions: Ma YL, Li HG, and Xu JX drafted the manuscript; Lu D and Xu X revised the manuscript.
AI contribution statement: Grammarly and an AI-based translation tool (ChatGPT) were used. The authors used Grammarly for language polishing and grammar checking, and an AI translation tool for translating or improving the fluency of certain sentences. Writing assistance (e.g., rephrasing or clarifying sentences) was also provided by AI. No AI tool was used for data analysis.
Conflict-of-interest statement: The authors declare that they have no competing interests.
Corresponding author: Di Lu, Department of Hepatobiliary & Pancreatic Surgery and Minimally Invasive Surgery, Zhejiang Provincial People's Hospital, No. 158 Shangtang Road, Hangzhou 310014, Zhejiang Province, China. zjuludi@zju.edu.cn
Received: November 24, 2025 Revised: January 20, 2026 Accepted: January 30, 2026 Published online: June 21, 2026 Processing time: 197 Days and 14.3 Hours
Abstract
We read with interest the study by Wang et al entitled “Interpretable machine learning model for early complication prediction after split liver transplantation”. Split liver transplantation (SLT) expands the donor pool but is associated with an increased risk of early postoperative complications (EPCs) due to extended resection surfaces and altered partial graft hemodynamics. This study aimed to develop an interpretable machine learning (ML) framework for identifying risk factors of EPCs in adult right trisegment SLT. A retrospective analysis was conducted on 109 recipients, of whom 37 developed EPCs. Four ML algorithms were employed, with random forest demonstrating optimal performance. SHapley Additive exPlanations (SHAP) analysis identified four independent predictors: Log-transformed systemic immune-inflammation index (LnSII), Model for End-Stage Liver Disease (MELD) score, partial lobectomy of segment IV, and intraoperative blood loss. The constructed diagnostic nomogram exhibited excellent discrimination and calibration. Survival analysis further revealed that LnSII and MELD score were significantly associated with five-year overall survival (P < 0.05). SHAP analysis bridges the gap between ML predictions and clinical decision-making, holding promising application prospects. However, the single-center retrospective design of this study imposes limitations, necessitating multicenter validation. Future research should incorporate dynamic postoperative variables and clarify the underlying biological mechanisms.
Core Tip: The study by Wang et al developed an interpretable machine learning model for predicting early complications after split liver transplantation. Through novel integration of multiple algorithms with SHapley Additive exPlanations (SHAP) analysis to identify the systemic immune inflammation index, the Model for End-Stage Liver Disease score, intraoperative blood loss, and the removal of the fourth segment of the liver lobe as independent predictive factors. The SHAP analysis also made the decision-making process of the model transparent and visible - not only did it globally display the ranking of the contribution of each factor, but it could also present the specific impact of each feature on the predicted risk of individual patients. Ultimately, a visual nomogram integrating inflammation, disease severity, surgical factors, and blood loss was produced. This is an important practice in advancing liver transplantation towards precision medicine.
